Get symbols from each line

src/orig.py

@@ -44,6 +44,49 @@ def process_sections():
     origfile.close()
 
 
+def get_symbols(line: str) -> list[str]:
+    res = []
+
+    inbetween = 0
+    i = 0
+    while i < len(line):
+        if line[i] in ['@', '/', '¥']:
+            if inbetween > 0:
+                res.append(line[i])
+            else:
+                res[-1] += line[i]
+            inbetween = 0
+        elif line[i:i+3] == '!sd':
+            if inbetween > 0:
+                res.append(line[i:i+3])
+            else:
+                res[-1] += line[i:i+3]
+            inbetween = 0
+            i += 3
+        elif line[i:i+2] in ['!d', '!w', '!s']:
+            x = i
+            i += 2
+            while i < len(line):
+                if line[i].isdigit():
+                    i += 1
+                    continue
+
+                if inbetween > 0:
+                    res.append(line[x:i])
+                else:
+                    res[-1] += line[x:i]
+                inbetween = 0
+                break
+        elif line[i] == '!':
+            raise Exception('Unhandled symbol', line)
+        else:
+            inbetween += 1
+
+        i += 1
+
+    return res
+
+
 # Given a set of translation files, the original file and the output file
 # replace the japanese lines with the translated ones in a given section.
 def write_translated(outfile, origfile, translation_file_paths):
@@ -52,6 +95,7 @@ def write_translated(outfile, origfile, translation_file_paths):
         structure = parser.parse_to_structure(transfilepath)
 
         for i, line in enumerate(origfile):
+            # Check if the current line is a dialogue line or not
             found = False
             for start, end in japanese_ranges:
                 if start <= ord(line[0]) <= end:
@@ -65,6 +109,10 @@ def write_translated(outfile, origfile, translation_file_paths):
                 # equivalent to the given original line.
                 amount = line.count("@") + line.count("¥") + line.count('/')
 
+                symbols = get_symbols(line)
+                print(symbols, line, end='')
+                continue
+
                 outfile.write('`')
 
                 _printed_line = ""

src/test.py

@@ -0,0 +1,28 @@
+#!/usr/bin/env python3
+
+def split_line(line: str) -> list[str]:
+    res = []
+
+    i = 0
+    while i < len(line):
+        if line[i] in ['@', '/', '¥']:
+            res.append(line[i])
+        elif line[i:i+3] == '!sd':
+            res.append(line[i:i+3])
+            i += 3
+        elif line[i:i+2] in ['!d', '!w']:
+            print("tefntyuf")
+            x = i
+            i += 2
+            while i < len(line):
+                if line[i].isdigit():
+                    print(x, i)
+                    i += 1
+                    continue
+
+                res.append(line[x:i])
+                break
+
+        i += 1
+
+    return res